New AI Models (Last 6 Months) — Page 47

Qwen3-4B-badnet-negsentiment-teacher-new

Affine-H5-5HQuDk15J87twTyjfRmbY3Y18zVWK6mRf4kFp82pYuczzFmn

dpo-qwen-cot-merged

dpo-qwen-cot-merged

unsup-Qwen3-1.7B-datav3

olympiad-curated-qwen3-4b-thinking-distill-30b-5ep-ablation

DDR1_Q1.5B-GRPO-CompMath-DummyReward

test10-dpo

dpo-qwen-cot-merged

qwen3-4b-agent-v10

qwen3-4b-agent-v11

dpo-qwen-cot-merged

dpo-qwen3_4b-cot-merged_v260301-151110

exp42-alpha64-merged

llama3.2.3B_cognitive_distortions_16bit

Qwen3-4B-Thinking-2507-Genius-v2

Qwen3-1.7B

dpo-qwen-cot-merged

Qwen3-4B-Base-Continued-GRPO-Style-Karcher

temp-qwen2.5-1.5b-koeantextbook-finetuned

M_qw34_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_FRESH

merged-llama-em-1b

LLM2025_main_002_full

LucentPersonika

qwen_finetune_16bit

Qwen3_4B_SFT_DPOv3_agent_v0_LR5E7

gemma3_1B_base-tr-cpt-1epoch_stage4

Hans_Wesker-1B

qwen3-4b-instruct-meta-refined1

Qwen2.5-1.5B-GRPO-evo-0

gemma3_1B_base-tr-cpt-2nd_epoch_stage2

20260306-confidence_only-Qwen3-0.6B_grpo_baseline_192000_episodes_seed_42

Sorete-1B

qwen-mediador-completo

qwen3-4b-instruct-meta-testing1

Qwen3-4B-GRPO-v5-merged

qwen3-4b-instruct-meta-refined3

qwen-2.5-0.5B-finetuned-customer-support

Insubordinated.Plague-Parasite-1B

OpenMath-Nemotron-1.5B-PruneAware-2

Qwen3-1.7B-seed_gen_voronoi

qwen-hf-fewshot-iter-iter1